“School of Cognitive Sciences”

Back to Papers Home
Back to Papers of School of Cognitive Sciences

Paper   IPM / Cognitive Sciences / 8365
School of Cognitive Sciences
  Title:   Identification of Hydroxyl Functional Group and Alcohol's by Near-Infrared Spectroscopy and Artificial Neural Network
  Author(s): 
1.  M. Babri
2.  S. Rouhani
3.  A. Massoumi
  Status:   Published
  Journal: Iranian J. Sci. Tech.
  No.:  4
  Vol.:  22
  Year:  1998
  Pages:   Transaction A
  Supported by:  IPM
  Abstract:
Hydroxy1 functional group identification has become possible without the use of reagents by using near-infrared (NIR) spectroscopy and artificial neural network (ANN). In this study, the NIR spectra of six components were fed to back propagation three-layer neural network as a training set and then the spectra of 33 chemicals were tested by ANN. The corresponding mathews correlation coefficient for classification task by ANN was calculated. With regard to training time and the error of prediction, a systematic approach was used to determine the number of hidden nodes of ANN. The activation of output nodes and the number of carbons in a series of aliphatic alcohols are highly correlated. Thus, the identification of alcohols with out the use of chemical reagents is also possible by this treatment. The information content of this system (NIR-ANN) for identification of hydroxy1 functional group and the series of aliphatic alcohols was calculated using Shannon's equation

Download TeX format
back to top
scroll left or right